CN110989595A - Laser SLAM method based on subgraph merging and pose optimization - Google Patents
Laser SLAM method based on subgraph merging and pose optimization Download PDFInfo
- Publication number
- CN110989595A CN110989595A CN201911222864.7A CN201911222864A CN110989595A CN 110989595 A CN110989595 A CN 110989595A CN 201911222864 A CN201911222864 A CN 201911222864A CN 110989595 A CN110989595 A CN 110989595A
- Authority
- CN
- China
- Prior art keywords
- pose
- optimization
- laser
- subgraph
- sub
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000005457 optimization Methods 0.000 title claims abstract description 35
- 230000006835 compression Effects 0.000 claims abstract description 10
- 238000007906 compression Methods 0.000 claims abstract description 10
- 238000012216 screening Methods 0.000 claims abstract description 7
- 230000009466 transformation Effects 0.000 claims abstract description 7
- 239000011159 matrix material Substances 0.000 claims description 6
- 230000002159 abnormal effect Effects 0.000 claims description 2
- 230000015572 biosynthetic process Effects 0.000 claims description 2
- 238000006243 chemical reaction Methods 0.000 claims description 2
- 238000005755 formation reaction Methods 0.000 claims description 2
- 238000013519 translation Methods 0.000 claims description 2
- 238000013507 mapping Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000004020 conductor Substances 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000010408 sweeping Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0257—Control of position or course in two dimensions specially adapted to land vehicles using a radar
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0276—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Aviation & Aerospace Engineering (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention discloses a laser SLAM method based on subgraph merging and pose optimization, which comprises the following steps: 1) acquiring environment information through scanning matching of a laser radar, mapping the laser information to a world coordinate system through inter-frame matching and coordinate transformation of laser data, and generating a sub-graph sequence; 2) optimizing pose information of the robot in the sub-graph sequence generated in the step 1); 3) adding the optimized subgraph and pose information into a candidate set, grading the candidate set according to a standard, and constructing an information table; 4) screening the information table in the step 3) to obtain a compression table, and then merging a plurality of subgraphs together according to a data association method; 5) carrying out global optimization on the multiple subgraphs; 6) generation of global grid map: and the robot continuously moves to visit different places until a global map is generated. The invention solves the global map limb into a plurality of subgraphs by using the idea of a divide-and-conquer method, and solves the global map optimization by solving the subgraph problem.
Description
Technical Field
The invention relates to a robot technology, in particular to a laser SLAM method based on subgraph merging and pose optimization.
Background
Mobile robots currently have applications in various industries, such as: AGVs in industrial-scale warehouse logistics; a patrol robot in the aspect of security; a welcome robot, a sweeping robot, etc. in the aspect of service; among the technologies of mobile robots, the robot SLAM technology is important. For the SLAM problem, the logistics AGV generally needs a fixed track, and the autonomy is low; the inspection robot lacks more excellent judgment capability on the obstacles; the service robot has poor adaptability to large-scale scenes. In addition, most robots are prone to accumulating errors in the moving process due to observation noise of the sensors in the positioning process, so that positioning failure and map distortion are caused.
Disclosure of Invention
The invention aims to solve the technical problem of providing a laser SLAM method based on subgraph merging and pose optimization aiming at the defects in the prior art.
The technical scheme adopted by the invention for solving the technical problems is as follows: a laser SLAM method based on sub-graph merging and pose optimization comprises the following steps:
1) acquiring environment information through laser radar scanning matching, wherein the concrete expression form of the environment information is laser data, and the laser data maps the laser information to a world coordinate system through inter-frame matching and coordinate transformation to generate a sub-graph sequence;
2) optimizing pose information of the robot in the sub-graph sequence generated in the step 1);
3) and adding the optimized subgraph and pose information into a candidate set, grading the candidate set according to a standard, and constructing an information table.
4) Screening the information table in the step 3) to obtain a compression table, and then merging a plurality of subgraphs together according to a data association method;
5) carrying out global optimization on the multiple subgraphs;
6) generation of global grid map: and the robot continuously moves to visit different places until a global map is generated.
According to the scheme, the specific method for generating the subgraph sequence in the step 1) is as follows:
step 1.1) defining the initial pose epsilon of the robot as (x, y, theta)TWherein (x, y)TRepresenting translation amount, and theta representing deflection amount, and obtaining the pose of the robot, namely a laser radar scanning frame, by the observation of a laser radar;
step 1.2) defining laser scanning beam end points in the 2D plane as h ═ (h ═ h)x,hy)TEach time the laser beam is scanned, one point set is generated, and the set of scanning points is described as H ═ Hi}i=1,...,n,hi∈R2;
Step 1.3) transformation of T by coordinatesεConverting the laser radar scanning frame into sub-image data, the conversion adopts the following formula
Step 1.4) laser scanning converts each pair of successively matched data into subgraphs by transformation.
According to the scheme, the pose of the robot optimized in the step 2) adopts a Gauss-Newton method.
According to the scheme, the attitude information in the step 2) is optimized by adopting the following formula
According to the scheme, the scoring in the step 3) adopts the following formula:
step 3.1) defining a bilinear interpolation function MNearestBest pose point (x ', y') in search grid (x, y)
In the formula (3), r is the maximum value of the step size of the search, and h is the multiple of the compressed grid;
in the formula (3), the bilinear interpolation function is defined as
Wherein P is11(x1,y1),P21(x2,y1),P12(x1,y2),P22(x2,y2) Are the four vertices in a square grid.
Step 3.2) defining a bilinear interpolation function M in the same way, and calculating the score of each pose point
According to the scheme, the step 4) screens the scoring result of the step 3) to obtain a compression table;
the screening method comprises the following steps:
compressing the information table according to the set multiple h of the compressed grid and the multiple of the power of 2, wherein the compression formula is as follows
C=I/2h(6)
Wherein, I and C respectively represent the grid numbers of the information table and the compression table.
According to the scheme, when global optimization is performed on the subgraphs in the step 5), the merged subgraphs are optimized by using a Ceres optimization library, so that the error after merging is reduced.
According to the scheme, when global optimization is carried out on the subgraphs in the step 5), a Ceres optimization library is adopted to optimize the merged subgraphs;
the specific method comprises the following steps:
the global optimization problem can be described as a non-linear least squares problem, as well as scan matching, and the Ceres optimization library is invoked to solve the non-linear least squares problem, which can be expressed as
Where ρ is the Huber loss function used to reduceThe influence of abnormal values caused by the scanning environment is low. Subgraph pose in global coordinate systemAnd scanning positionThe optimization is performed by giving some constraints.
In the optimization method, the residual error of the subgraph constraint is calculated by the following formula
These constraints take the form of relative formations ξijAnd associated covariance matrix ∑ij. For a set of subgraphs i and j, the pose ε of the subgraph coordinate systemijDescribing scan matching, covariance matrix ∑ijThe features may be estimated.
The invention has the following beneficial effects:
1. the method is based on the most advanced graph optimization SLAM framework, the global map limb is decomposed into a plurality of subgraphs by using the idea of a divide-and-conquer method, and the global map is solved by solving the problem of the subgraphs;
2. the invention extracts and locally optimizes the formed subgraph in the front-end data acquisition stage of SLAM, and reduces errors caused by sensor observation. At the back end, the feature data association is utilized to merge the subgraphs and optimize multiple sub-maps, so that the accumulated error is further reduced.
Drawings
The invention will be further described with reference to the accompanying drawings and examples, in which:
FIG. 1 is a flow chart of a method of an embodiment of the present invention;
FIG. 2 is a schematic view of a robot according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a test scenario and a predetermined trajectory according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a laser interframe matching process according to an embodiment of the invention;
FIG. 5 is a schematic diagram of a candidate set and scoring according to an embodiment of the present invention;
FIG. 6 is a schematic diagram of a candidate set screening process according to an embodiment of the invention;
FIG. 7 is a comparison graph of closed loop detection and global map rectification according to an embodiment of the present invention;
FIG. 8 is a graph comparing the method of the present invention with a conventional method.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail with reference to the following embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
As shown in fig. 1, a SLAM method based on sub-graph merging and pose optimization includes the following steps:
step 1, a ground mobile robot is adopted, surrounding environment information is collected through a sensor, and a sub-graph sequence is created according to the information;
in this embodiment, referring to fig. 2, the robot in step 1 is an omnidirectional mobile robot and must be equipped with a laser radar sensor.
In this embodiment, referring to fig. 3, the robot travels according to a predetermined trajectory. When the laser data reaches a certain value, see fig. 4, the laser data will be inter-frame matched, transformed by formula (1) SiAnd (epsilon), mapping the laser information of the robot into a global coordinate system, and further generating a subgraph sequence.
in the embodiment, the problem of finding the optimal point by laser scanning matching is converted into a nonlinear optimization problem, and the optimized pose is
Where the M function is a bicubic interpolation (bicubic interpolation) smoothing function that returns the coordinate values of the sub-map from the laser scan frame. Giving an initial pose epsilon, defining and estimating delta epsilon, and enabling an observation error to be minimum, then
M (S) by first order Taylor expansioni(. epsilon. + Δ. epsilon.)), can be obtained
Solving for Δ ε by Gauss-Newton method to minimize
Wherein H is a Hessian Matrix (Hessian Matrix) of
Where the subgraph gradient is approximately represented as ▽ M (S)i(. epsilon.)), and the formula (1) can be obtained
Step 3, adding the optimized sub-graph information into a candidate set, and scoring the candidate set according to a certain standard;
in this embodiment, referring to fig. 5, it is a candidate set of the method, and each number in the set is scored according to formula (3) and formula (5), and the score is a percentage system, and the maximum value does not exceed 1.
In this embodiment, referring to fig. 6, a candidate set screening process of the method is described, that is, a maximum value in a table is selected to form a new table, where the grid compression factor h is 2.
in this embodiment, referring to fig. 6, according to the scoring criterion in step 3, a pose score is calculated, and the sub-graph data with the highest score is selected. And (4) in consideration of the consistency of the characteristic sequence, merging the multiple subgraphs together according to a data association method.
Step 5, optimizing the merged subgraphs by using a Ceres nonlinear optimization library;
in this embodiment, as shown in fig. 7, the map is distorted due to the accumulation of the robot motion errors, and the map is corrected after Ceres optimization.
In this embodiment, the mobile robot moves continuously, and when a known location is visited again, the mobile robot is associated with previous data to achieve a closed loop and achieve the purpose of map correction.
And 6, forming a global grid map.
In this embodiment, referring to fig. 7, the mobile robot moves continuously, visits an unknown place, generates subgraphs continuously, and performs step 4 and step 5; when multiple visits are made to the known place, the map information generated by the visits is in relevance matching with the previously generated information, and the score exceeds 0.95, new subgraphs cannot be added, and the step 5 is executed until the global map is generated.
In the embodiment, as shown in fig. 8, it can be seen visually that the map obtained by the method is finer, the details of the map are clearer, and the method is more superior to the traditional mapping and conductor SLAM methods.
It will be understood that modifications and variations can be made by persons skilled in the art in light of the above teachings and all such modifications and variations are intended to be included within the scope of the invention as defined in the appended claims.
Claims (8)
1. A laser SLAM method based on subgraph merging and pose optimization is characterized by comprising the following steps:
1) acquiring environment information through scanning matching of a laser radar, wherein the expression form of the environment information is laser data, and the laser data maps the laser information to a world coordinate system through inter-frame matching and coordinate transformation to generate a sub-graph sequence;
2) optimizing pose information of the robot in the sub-graph sequence generated in the step 1);
3) adding the optimized subgraph and pose information into a candidate set, grading the candidate set according to a standard, and constructing an information table;
4) screening the information table in the step 3) to obtain a compression table, and then merging a plurality of subgraphs together according to a data association method;
5) carrying out global optimization on the multiple subgraphs;
6) generation of global grid map: and the robot continuously moves to visit different places until a global map is generated.
2. The sub-graph merging and pose optimization-based laser SLAM method according to claim 1, wherein the specific method for generating sub-graph sequences in step 1) is as follows:
step 1.1) defining the initial pose epsilon of the robot as (x, y, theta)TWherein (x, y)TRepresenting translation amount, and theta representing deflection amount, and obtaining the pose of the robot, namely a laser radar scanning frame, by the observation of a laser radar;
step 1.2) defining laser scanning beam end points in the 2D plane as h ═ (h ═ h)x,hy)TEach time the laser beam is scanned, one point set is generated, and the set of scanning points is described as H ═ Hi}i=1,...,n,hi∈R2;
Step 1.3) transformation of T by coordinatesεConverting the laser radar scanning frame into sub-image data, the conversion adopts the following formula
Step 1.4) laser scanning converts each pair of successively matched data into subgraphs by transformation.
3. The subgraph merging and pose optimization-based laser SLAM method according to claim 1, wherein the pose of the robot optimized in step 2) is Gaussian Newton method.
5. The subgraph merging and pose optimization-based laser SLAM method according to claim 1, wherein the scoring of step 3) adopts the following formula:
step 3.1) defining a bilinear interpolation function MNearestBest pose point (x ', y') in search grid (x, y)
In the formula (3), r is the maximum value of the step size of the search, and h is the multiple of the compressed grid;
in the formula (3), the bilinear interpolation function is defined as
Wherein P is11(x1,y1),P21(x2,y1),P12(x1,y2),P22(x2,y2) Are the four vertices in a square grid.
Step 3.2) defining a bilinear interpolation function M in the same way, and calculating the score of each pose point
6. The subgraph merging and pose optimization-based laser SLAM method according to claim 1, wherein the step 4) screens the scoring results of the step 3) to obtain a compression table;
the screening method comprises the following steps:
compressing the information table according to the set multiple h of the compressed grid and the multiple of the power of 2, wherein the compression formula is as follows
C=I/2h(6)
Wherein, I and C respectively represent the grid numbers of the information table and the compression table.
7. The sub-graph merging and pose optimization-based laser SLAM method according to claim 1, wherein a Ceres optimization library is adopted to optimize the merged sub-graphs in the step 5) when the sub-graphs are globally optimized, so as to reduce errors after merging.
8. The sub-graph merging and pose optimization-based laser SLAM method according to claim 1, wherein the merged sub-graphs are optimized by a Ceres optimization library when the sub-graphs are globally optimized in the step 5);
the specific method comprises the following steps:
calling Ceres optimization library to solve the non-linear least squares problem, expressed as
Wherein rho is a Huber loss function and is used for reducing the influence caused by abnormal values generated due to scanning environment, and the subgraph pose in the global coordinate systemAnd scanning positionOptimizing by giving constraint conditions;
in the optimization method, the residual error of the subgraph constraint is calculated by the following formula
These constraints take the form of relative formations ξijAnd associated covariance matrix ∑ijFor a set of subgraphs i and scans j, the pose ε of the subgraph coordinate systemijDescribing scan matching, covariance matrix ∑ijThe features are estimated.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911222864.7A CN110989595A (en) | 2019-12-03 | 2019-12-03 | Laser SLAM method based on subgraph merging and pose optimization |
AU2020101833A AU2020101833A4 (en) | 2019-12-03 | 2020-08-14 | Laser slam method based on subgraph merging and pose optimization |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911222864.7A CN110989595A (en) | 2019-12-03 | 2019-12-03 | Laser SLAM method based on subgraph merging and pose optimization |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110989595A true CN110989595A (en) | 2020-04-10 |
Family
ID=70089763
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911222864.7A Pending CN110989595A (en) | 2019-12-03 | 2019-12-03 | Laser SLAM method based on subgraph merging and pose optimization |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN110989595A (en) |
AU (1) | AU2020101833A4 (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111643008A (en) * | 2020-05-13 | 2020-09-11 | 深圳市银星智能科技股份有限公司 | Expanded partition cleaning method and device and computer readable storage medium |
CN112462385A (en) * | 2020-10-21 | 2021-03-09 | 南开大学 | Map splicing and positioning method based on laser radar under outdoor large environment |
CN113514843A (en) * | 2021-07-09 | 2021-10-19 | 深圳华芯信息技术股份有限公司 | Multi-subgraph laser radar positioning method and system and terminal |
CN113532421A (en) * | 2021-06-30 | 2021-10-22 | 同济人工智能研究院(苏州)有限公司 | Dynamic laser SLAM method based on subgraph updating and reflector optimization |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112581610B (en) * | 2020-10-16 | 2023-06-13 | 武汉理工大学 | Robust optimization method and system for building map from multi-beam sonar data |
CN112665575B (en) * | 2020-11-27 | 2023-12-29 | 重庆大学 | SLAM loop detection method based on mobile robot |
CN113587933B (en) * | 2021-07-29 | 2024-02-02 | 山东山速机器人科技有限公司 | Indoor mobile robot positioning method based on branch-and-bound algorithm |
CN113947636B (en) * | 2021-10-19 | 2024-04-26 | 中南大学 | Laser SLAM positioning system and method based on deep learning |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109541630A (en) * | 2018-11-22 | 2019-03-29 | 武汉科技大学 | A method of it is surveyed and drawn suitable for Indoor environment plane 2D SLAM |
CN109978767A (en) * | 2019-03-27 | 2019-07-05 | 集美大学 | The ground laser SLAM drawing method based on multirobot collaboration |
CN110119144A (en) * | 2019-04-19 | 2019-08-13 | 苏州大学 | Based on the matched multirobot SLAM algorithm of sub- map feature |
-
2019
- 2019-12-03 CN CN201911222864.7A patent/CN110989595A/en active Pending
-
2020
- 2020-08-14 AU AU2020101833A patent/AU2020101833A4/en not_active Ceased
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109541630A (en) * | 2018-11-22 | 2019-03-29 | 武汉科技大学 | A method of it is surveyed and drawn suitable for Indoor environment plane 2D SLAM |
CN109978767A (en) * | 2019-03-27 | 2019-07-05 | 集美大学 | The ground laser SLAM drawing method based on multirobot collaboration |
CN110119144A (en) * | 2019-04-19 | 2019-08-13 | 苏州大学 | Based on the matched multirobot SLAM algorithm of sub- map feature |
Non-Patent Citations (3)
Title |
---|
WOLFGANG HESS,等: "Real-Time Loop Closure in 2D LIDAR SLAM", 《2016 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA)》 * |
徐博: "基于位姿估计闭环检测的激光SLAM算法研究", 《万方硕士学位论文》 * |
文国成,等: "一种适用于激光SLAM大尺度地图的闭环检测方法", 《计算机应用研究》 * |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111643008A (en) * | 2020-05-13 | 2020-09-11 | 深圳市银星智能科技股份有限公司 | Expanded partition cleaning method and device and computer readable storage medium |
CN111643008B (en) * | 2020-05-13 | 2021-11-16 | 深圳市银星智能科技股份有限公司 | Expanded partition cleaning method and device and computer readable storage medium |
CN112462385A (en) * | 2020-10-21 | 2021-03-09 | 南开大学 | Map splicing and positioning method based on laser radar under outdoor large environment |
CN113532421A (en) * | 2021-06-30 | 2021-10-22 | 同济人工智能研究院(苏州)有限公司 | Dynamic laser SLAM method based on subgraph updating and reflector optimization |
CN113532421B (en) * | 2021-06-30 | 2024-04-26 | 同济人工智能研究院(苏州)有限公司 | Dynamic laser SLAM method based on subgraph updating and reflector optimization |
CN113514843A (en) * | 2021-07-09 | 2021-10-19 | 深圳华芯信息技术股份有限公司 | Multi-subgraph laser radar positioning method and system and terminal |
Also Published As
Publication number | Publication date |
---|---|
AU2020101833A4 (en) | 2020-09-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110989595A (en) | Laser SLAM method based on subgraph merging and pose optimization | |
CN112014857B (en) | Three-dimensional laser radar positioning and navigation method for intelligent inspection and inspection robot | |
CN110689622B (en) | Synchronous positioning and composition method based on point cloud segmentation matching closed-loop correction | |
WO2021196294A1 (en) | Cross-video person location tracking method and system, and device | |
CN113409410B (en) | Multi-feature fusion IGV positioning and mapping method based on 3D laser radar | |
CN114862932B (en) | BIM global positioning-based pose correction method and motion distortion correction method | |
CN111540005A (en) | Loop detection method based on two-dimensional grid map | |
CN115774265B (en) | Two-dimensional code and laser radar fusion positioning method and device for industrial robot | |
CN103136525A (en) | Hetero-type expanded goal high-accuracy positioning method with generalized Hough transposition | |
CN116449384A (en) | Radar inertial tight coupling positioning mapping method based on solid-state laser radar | |
Kang et al. | Range image techniques for fast detection and quantification of changes in repeatedly scanned buildings | |
CN117808964A (en) | BIM-based steel structure deformation monitoring and processing method and system | |
Sheng et al. | Mobile robot localization and map building based on laser ranging and PTAM | |
CN115267724B (en) | Position re-identification method of mobile robot capable of estimating pose based on laser radar | |
CN113947636B (en) | Laser SLAM positioning system and method based on deep learning | |
CN111239761B (en) | Method for indoor real-time establishment of two-dimensional map | |
Dai et al. | Geographic planning and design of marine island ecological landscape based on genetic algorithm | |
CN115512054A (en) | Method for constructing three-dimensional space-time continuous point cloud map | |
CN115355904A (en) | Slam method for Lidar-IMU fusion of ground mobile robot | |
CN108090961B (en) | Rapid adjustment method in three-dimensional laser point cloud imaging | |
Dong et al. | Efficient feature extraction and localizability based matching for lidar slam | |
Chen et al. | An improved Snake model for refinement of LiDAR-derived building roof contours using aerial images | |
Zheng et al. | Research of Coverage Evaluation of Cleaning Robots based on visual perception | |
Wu et al. | Building Facade Reconstruction Using Crowd-Sourced Photos and Two-Dimensional Maps | |
Ren et al. | Lidar-only 3D SLAM System Comparative Study |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200410 |
|
RJ01 | Rejection of invention patent application after publication |